mule-image/backend/app/config.py

"""
Application configuration using Pydantic Settings
"""
from pydantic_settings import BaseSettings
from pydantic import BaseModel, Field
from typing import Optional
import yaml
from pathlib import Path

class ThumbnailSettings(BaseModel):
    """Thumbnail generation settings"""
    small: int = 240
    medium: int = 640
    large: int = 1280
    quality: int = 85
    format: str = "webp"

class ScannerSettings(BaseModel):
    """File scanner settings"""
    watch: bool = True
    initial_scan_on_start: bool = True
    batch_size: int = 100
    concurrent_workers: int = 4

class PerformanceSettings(BaseModel):
    """Performance tuning settings"""
    max_concurrent_thumbnails: int = 10
    cache_ttl: int = 3600
    db_pool_size: int = 20
    db_pool_recycle: int = 3600

class EmbedderSettings(BaseModel):
    """CLIP / SigLIP embedding model settings"""
    name: str = "openclip_vitb32"
    batch_size: int = 8

class OCRSettings(BaseModel):
    """PaddleOCR / rapidocr settings"""
    enabled: bool = True
    languages: list[str] = ["en"]
    min_confidence: float = 0.5

class DetectorSettings(BaseModel):
    """YOLOv8n object detection settings"""
    enabled: bool = True
    min_confidence: float = 0.35
    max_detections: int = 50

class FacesSettings(BaseModel):
    """YuNet + SFace face detection/recognition settings"""
    enabled: bool = True
    min_face_size: int = 40
    recognition_threshold: float = 0.65
    cluster_eps: float = 0.5

class ClassifierSettings(BaseModel):
    """CLIP zero-shot content classification settings"""
    enabled: bool = True
    min_confidence: float = 0.3

class VisionSettings(BaseModel):
    """AI vision pipeline settings. Disabled when running on SQLite
    (pgvector is required for embedding storage)."""
    enabled: bool = True
    backend: str = "onnx"           # "onnx" | "rocm" (future)
    models_dir: str = "/data/models"
    embedder: EmbedderSettings = EmbedderSettings()
    ocr: OCRSettings = OCRSettings()
    detector: DetectorSettings = DetectorSettings()
    faces: FacesSettings = FacesSettings()
    classifier: ClassifierSettings = ClassifierSettings()
    worker_concurrency: int = 2

class MulitaConfig(BaseModel):
    """Main configuration from YAML file. Source roots and the discard
    workflow are owned by the database now — only operational settings
    live here."""
    thumbnails: ThumbnailSettings = ThumbnailSettings()
    scanner: ScannerSettings = ScannerSettings()
    performance: PerformanceSettings = PerformanceSettings()
    vision: VisionSettings = VisionSettings()

class Settings(BaseSettings):
    """Application settings"""
    # Database — Postgres + pgvector by default. The SQLite escape hatch
    # remains supported via the docker-compose.sqlite.yml override and by
    # setting DATABASE_URL=sqlite+aiosqlite:///... in .env for local dev.
    database_url: str = Field(
        default="postgresql+asyncpg://mulita:mulita@db:5432/mulita",
        env="DATABASE_URL"
    )
    
    # Redis
    redis_url: str = Field(
        default="redis://localhost:6379",
        env="REDIS_URL"
    )
    
    # Celery
    celery_broker_url: str = Field(
        default="redis://localhost:6379",
        env="CELERY_BROKER_URL"
    )
    celery_result_backend: str = Field(
        default="redis://localhost:6379",
        env="CELERY_RESULT_BACKEND"
    )
    
    # Photo directories
    photo_dirs: str = Field(
        default="/photos",
        env="PHOTO_DIRS"
    )
    
    # API settings
    api_host: str = Field(default="0.0.0.0", env="API_HOST")
    api_port: int = Field(default=8000, env="API_PORT")

    # CORS — comma-separated list of allowed origins, or "*" for any.
    # Same-origin requests (the normal case behind nginx / vite proxy)
    # never trip CORS, so this is only for direct browser access from
    # other origins (LAN IP, reverse proxy, dev tools).
    allowed_origins: str = Field(default="*", env="ALLOWED_ORIGINS")

    # Logging — accepts standard python levels (DEBUG, INFO, WARNING,
    # ERROR, CRITICAL). Bumped from INFO when chasing a problem.
    log_level: str = Field(default="INFO", env="LOG_LEVEL")

    @property
    def cors_origins(self) -> list[str]:
        """Parse the ALLOWED_ORIGINS env var into a list. Accepts:
          - "*" → wildcard (single-element list ["*"])
          - "http://a.com,http://b.com" → split + strip
        Empty entries are dropped.
        """
        raw = (self.allowed_origins or "").strip()
        if not raw or raw == "*":
            return ["*"]
        return [o.strip() for o in raw.split(",") if o.strip()]

    # App configuration from YAML
    _config: Optional[MulitaConfig] = None
    
    @property
    def config(self) -> MulitaConfig:
        """Load configuration from YAML file"""
        if self._config is None:
            config_path = Path("/app/config/mulita.yml")
            if not config_path.exists():
                config_path = Path("mulita.yml")
            
            if config_path.exists():
                with open(config_path, "r") as f:
                    config_data = yaml.safe_load(f)
                    self._config = MulitaConfig(**config_data)
            else:
                self._config = MulitaConfig()
        
        return self._config
    
    @property
    def thumbnails(self) -> ThumbnailSettings:
        return self.config.thumbnails
    
    @property
    def scanner(self) -> ScannerSettings:
        return self.config.scanner

    @property
    def performance(self) -> PerformanceSettings:
        return self.config.performance

    @property
    def vision(self) -> VisionSettings:
        return self.config.vision

    class Config:
        env_file = ".env"
        case_sensitive = False

# Global settings instance
settings = Settings()